SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09305 · 2021

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
cure-lab/SCINet canonical 1 of 1
HiddeKanger/SCINet pwc_unofficial 1 of 5
FunctionStatusWhere it lives
get_variable Ran cure-lab/SCINet/models/SCINet.py
code served (permissive licence) · get_code("f4796d7c5da2f9ca")
unique_cols Ran HiddeKanger/SCINet/base/preprocess_data.py
code served (permissive licence) · get_code("c880687cb3cf3e16")
match_data Not yet run HiddeKanger/SCINet/exp/live_trading/utils/live_scinet.py
code served (permissive licence) · get_code("8428bb3b71dee6e6")
match_data Not yet run HiddeKanger/SCINet/base/preprocess_data.py
code served (permissive licence) · get_code("e3f6538295dc7600")
preprocess Not yet run HiddeKanger/SCINet/base/preprocess_data.py
code served (permissive licence) · get_code("2c4032b3c091dc65")
scinet_builder Not yet run HiddeKanger/SCINet/base/SCINet.py
code served (permissive licence) · get_code("1a7780c7bde63e23")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose a novel neural network architecture that conducts sample convolution and interaction for temporal modeling and forecasting, named SCINet. Specifically, SCINet is a recursive downsample-convolve-interact architecture. In each layer, we use multiple convolutional filters to extract distinct yet valuable temporal features from the downsampled sub-sequences or features. By combining these rich features aggregated from multiple resolutions, SCINet effectively models time series with complex temporal dynamics. Experimental results show that SCINet achieves significant forecasting accuracy improvements over both existing convolutional models and Transformer-based solutions across various real-world time series forecasting datasets. Our codes and data are available at https://github.com/cure-lab/SCINet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.09305")
get_code_for_paper("2106.09305")
have("2106.09305")

Connect an agent — have() is free.